Hi all, (please see my questions at the bottom in bold, the rest of this is just giving context for my analysis)
I'm new to ArcGIS Pro and I'm trying to conduct a hotspot analysis of the rates of a disease by census tract using this paper's "5-step geoprocessing" approach: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4011116/
Step 1 of the approach says the following:
To understand the degree of size variation in California’s 7049 census tracts, we calculated the square mile area of all census tracts in the state. We considered census tracts that possessed a square mile area greater than 1.5 standard deviations above the state mean census tract area outliers (n = 118) and temporarily removed them from the dataset. In addition, we also removed small census tracts that had been adjacent to the removed ones (and appeared as “islands”; n = 11). This allowed us to begin to control for variability in census tract size in the next step of the analysis, considering census tracts of homogeneous geographic sizes.
The paper then used the non-outlier tracts to find the appropriate distance band using incremental spatial autocorrelation in the subsequent steps and after finding the band brings the outlier and island tracts back and encodes their relationships/neighbors in a spatial weights matrix. The non-outlier tracts use the previously found distance band and the outlier and island tracts use nearest two neighbors even if the distance is greater than the distance band.
I've calculated the AREA in square miles for each census tract using "Calculate Geometry" via the attributes table, and then calculated the average and standard deviation of all the tracts using "Summarize" via the attributes table. I then created a new field that contains the standard deviation times 1.5.
Finally I then used "Select by Attribute" to select all the census tracts where AREA > 1.5 times the standard deviation value I calculated. I then created a "dummy"/indicator variable that has a value of 1 for those tracts with an AREA > 1.5 times the standard deviation value and 0 for those with an AREA value lower than 1.5 times the standard deviation (this indicator variable probably isnt necessary).
Now that I have all these > 1.5 standard deviation outlier tracts selected how can I remove them in a way that lets me bring them back after I've used the remaining non-outlier tracts to to get the distance band using incremental spatial autocorrelation? Simply deleting them would not allow me to bring them back for the subsequent steps.
And what tool can I use in ArcGIS Pro to identify the 'island' census tracts after temporarily removing the outlier tracts?
